Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3187 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.4449. Min Range: -6.4449

Max Act: 6.4449. Min Act: 0.0000

Data Index: 846516 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 6.4449. Min Range: -6.4449

Max Act: 6.2860. Min Act: -0.0000

Data Index: 918756 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 6.4449. Min Range: -6.4449

Max Act: 6.2802. Min Act: -0.0000

Data Index: 788150 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 6.4449. Min Range: -6.4449

Max Act: 6.0188. Min Act: -0.0000

Data Index: 1326419 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 6.4449. Min Range: -6.4449

Max Act: 6.2122. Min Act: 0.0000

Data Index: 952893 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 6.4449. Min Range: -6.4449

Max Act: 6.2100. Min Act: -0.0000

Data Index: 1258676 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 6.4449. Min Range: -6.4449

Max Act: 6.3125. Min Act: -0.0000

Data Index: 115655 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 6.4449. Min Range: -6.4449

Max Act: 6.1924. Min Act: 0.0000

Data Index: 217079 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 6.4449. Min Range: -6.4449

Max Act: 5.9515. Min Act: -0.0000

Data Index: 787834 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 6.4449. Min Range: -6.4449

Max Act: 5.9543. Min Act: -0.0000

Data Index: 773492 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 6.4449. Min Range: -6.4449

Max Act: 5.9364. Min Act: 0.0000

Data Index: 641980 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 6.4449. Min Range: -6.4449

Max Act: 6.1183. Min Act: -0.0000

Data Index: 878050 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 6.4449. Min Range: -6.4449

Max Act: 5.6037. Min Act: -0.0000

Data Index: 412873 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 6.4449. Min Range: -6.4449

Max Act: 6.0429. Min Act: 0.0000

Data Index: 918431 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 6.4449. Min Range: -6.4449

Max Act: 5.7467. Min Act: -0.0000

Data Index: 407402 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 6.4449. Min Range: -6.4449

Max Act: 5.9404. Min Act: -0.0000

Data Index: 902577 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 6.4449. Min Range: -6.4449

Max Act: 5.7347. Min Act: 0.0000

Data Index: 104959 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 6.4449. Min Range: -6.4449

Max Act: 5.0434. Min Act: -0.0000

Data Index: 1256159 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 6.4449. Min Range: -6.4449

Max Act: 5.5738. Min Act: -0.0000

Data Index: 1319254 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 6.4449. Min Range: -6.4449

Max Act: 5.3092. Min Act: 0.0000

Data Index: 857912 (C4 (Web Text))

Max Activating Token Index: 256